diff --git a/rllib/examples/documentation/rllib_on_ray_readme.py b/rllib/examples/documentation/rllib_on_ray_readme.py
index 418faea869f0..27d121e4addc 100644
--- a/rllib/examples/documentation/rllib_on_ray_readme.py
+++ b/rllib/examples/documentation/rllib_on_ray_readme.py
@@ -24,16 +24,20 @@ def __init__(self, config):
         self.observation_space = gym.spaces.Box(0.0, self.end_pos, shape=(1,))
 
     def reset(self, *, seed=None, options=None):
-        """Resets the episode and returns the initial observation of the new one."""
+        """Resets the episode.
+
+        Returns:
+           Initial observation of the new episode and an info dict.
+        """
         self.cur_pos = 0
         # Return initial observation.
         return [self.cur_pos], {}
 
     def step(self, action):
-        """Takes a single step in the episode given `action`
+        """Takes a single step in the episode given `action`.
 
         Returns:
-            New observation, reward, done-flag, info-dict (empty).
+            New observation, reward, terminated-flag, truncated-flag, info-dict (empty).
         """
         # Walk left.
         if action == 0 and self.cur_pos > 0:
@@ -41,11 +45,12 @@ def step(self, action):
         # Walk right.
         elif action == 1:
             self.cur_pos += 1
-        # Set `done` and `truncated` flags when end of corridor (goal) reached.
-        done = truncated = self.cur_pos >= self.end_pos
+        # Set `terminated` flag when end of corridor (goal) reached.
+        terminated = self.cur_pos >= self.end_pos
+        truncated = False
         # +1 when goal reached, otherwise -1.
-        reward = 1.0 if done else -0.1
-        return [self.cur_pos], reward, done, truncated, {}
+        reward = 1.0 if terminated else -0.1
+        return [self.cur_pos], reward, terminated, truncated, {}
 
 
 # Create an RLlib Algorithm instance from a PPOConfig object.
@@ -78,15 +83,15 @@ def step(self, action):
 env = SimpleCorridor({"corridor_length": 10})
 # Get the initial observation (should be: [0.0] for the starting position).
 obs, info = env.reset()
-done = False
+terminated = truncated = False
 total_reward = 0.0
 # Play one episode.
-while not done:
+while not terminated and not truncated:
     # Compute a single action, given the current observation
     # from the environment.
     action = algo.compute_single_action(obs)
     # Apply the computed action in the environment.
-    obs, reward, done, truncated, info = env.step(action)
+    obs, reward, terminated, truncated, info = env.step(action)
     # Sum up rewards for reporting purposes.
     total_reward += reward
 # Report results.